Hugging Face's logo

mradermacher
/
Meta-Llama-3-70B-Instruct-DPO-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
conversational
Model card Files Community
mradermacher commited on
Commit
8dad31f
•
1 Parent(s): a586f8d

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -29,7 +29,7 @@ more details, including on how to concatenate multi-part files.
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
32
- | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | for the desperate |
33
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
35
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
@@ -50,7 +50,6 @@ more details, including on how to concatenate multi-part files.
50
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.1 | |
51
  | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
52
 
53
-
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
56
 
 
29
  | Link | Type | Size/GB | Notes |
30
  |:-----|:-----|--------:|:------|
31
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ1_S.gguf) | i1-IQ1_S | 15.4 | for the desperate |
32
+ | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ1_M.gguf) | i1-IQ1_M | 16.9 | mostly desperate |
33
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 19.2 | |
34
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 21.2 | |
35
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-IQ2_S.gguf) | i1-IQ2_S | 22.3 | |
 
50
  | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 50.1 | |
51
  | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-70B-Instruct-DPO-i1-GGUF/resolve/main/Meta-Llama-3-70B-Instruct-DPO.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 58.0 | practically like static Q6_K |
52
 
 
53
  Here is a handy graph by ikawrakow comparing some lower-quality quant
54
  types (lower is better):
55